Optimization-Based Data Generation for Photo Enhancement
Abstract
The preparation of large amounts of high-quality training data has always been the bottleneck for the performance of supervised learning methods. It is especially time-consuming for complicated tasks such as photo enhancement. A recent approach to ease data annotation creates realistic training data automatically with optimization. In this paper, we improve upon this approach by learning image-similarity which, in combination with a Covariance Matrix Adaptation optimization method, allows us to create higher quality training data for enhancing photos. We evaluate our approach on challenging real world photo-enhancement images by conducting a perceptual user study, which shows that its performance compares favorably with existing approaches.
Cite
Text
Omiya et al. "Optimization-Based Data Generation for Photo Enhancement." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00240Markdown
[Omiya et al. "Optimization-Based Data Generation for Photo Enhancement." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/omiya2019cvprw-optimizationbased/) doi:10.1109/CVPRW.2019.00240BibTeX
@inproceedings{omiya2019cvprw-optimizationbased,
title = {{Optimization-Based Data Generation for Photo Enhancement}},
author = {Omiya, Mayu and Horiuchi, Yusuke and Simo-Serra, Edgar and Iizuka, Satoshi and Ishikawa, Hiroshi},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {1890-1898},
doi = {10.1109/CVPRW.2019.00240},
url = {https://mlanthology.org/cvprw/2019/omiya2019cvprw-optimizationbased/}
}